English
Related papers

Related papers: SLAY: Geometry-Aware Spherical Linearized Attentio…

200 papers

As a common method in the field of computer vision, spatial attention mechanism has been widely used in semantic segmentation of remote sensing images due to its outstanding long-range dependency modeling capability. However, remote sensing…

Image and Video Processing · Electrical Eng. & Systems 2025-01-24 Xiaowen Ma , Rongrong Lian , Zhenkai Wu , Renxiang Guan , Tingfeng Hong , Mengjiao Zhao , Mengting Ma , Jiangtao Nie , Zhenhong Du , Siyang Song , Wei Zhang

Traffic forecasting represents a crucial problem within intelligent transportation systems. In recent research, Large Language Models (LLMs) have emerged as a promising method, but their intrinsic design, tailored primarily for sequential…

Machine Learning · Computer Science 2025-09-18 Hyotaek Jeon , Hyunwook Lee , Juwon Kim , Sungahn Ko

Visual localization is considered to be one of the crucial parts in many robotic and vision systems. While state-of-the art methods that relies on feature matching have proven to be accurate for visual localization, its requirements for…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Huy-Hoang Bui , Bach-Thuan Bui , Quang-Vinh Tran , Yasuyuki Fujii , Joo-Ho Lee

Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of RC*C (by compressing spatial dimensions) or RHW*HW (by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Qi Song , Jie Li , Chenghong Li , Hao Guo , Rui Huang

We propose an innovative, learnable two-sided short-time Laplace transform (STLT) mechanism to supplant the traditional self attention in transformer-based LLMs. Our STLT introduces trainable parameters for each Laplace node, enabling…

Machine Learning · Computer Science 2025-06-23 Andrew Kiruluta

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Machine Learning · Computer Science 2019-06-11 Linfeng Zhang , Zhanhong Tan , Jiebo Song , Jingwei Chen , Chenglong Bao , Kaisheng Ma

We introduce a simple spherical model whose structural properties are similar to the ones generated by models with directional interactions, by employing a binary mixture of large and small hard spheres, with a square-well attraction acting…

Disordered Systems and Neural Networks · Physics 2009-11-13 Emanuela Zaccarelli , Francesco Sciortino , Piero Tartaglia

Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Xuecheng Wu , Junxiao Xue , Liangyu Fu , Jiayu Nie , Danlei Huang , Xinyi Yin

Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator…

Quantum Physics · Physics 2025-10-14 Peng Du , Jinjing Shi , Wenxuan Wang , Yin Ma , Kai Wen , Xuelong Li

This paper presents a state-of-the-art approach in object detection for being applied in future SLAM problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face…

Robotics · Computer Science 2018-10-05 Seyed Amir Tafrishi , Vahid E. Kandjani

We study the problem of learning a low-degree spherical polynomial of degree $\ell_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network (NN) with channel attention in this…

Machine Learning · Statistics 2026-04-28 Yingzhen Yang

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Xizhou Zhu , Dazhi Cheng , Zheng Zhang , Stephen Lin , Jifeng Dai

Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hindering scalability to longer sequences. We introduce…

Machine Learning · Computer Science 2026-01-06 Yoshihiro Yamada

Foundation models have transformed language, vision, and time series data analysis, yet progress on dynamic predictions for physical systems remains limited. Given the complexity of physical constraints, two challenges stand out. $(i)$…

Machine Learning · Computer Science 2026-02-05 Haoran Li , Chenhan Xiao , Lihao Mai , Yang Weng , Erik Blasch

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

We propose AXELRAM, a smart SRAM macro architecture that computes attention scores directly from quantized KV cache indices without dequantization. The key enabler is a design-time fixed codebook: orthogonal-transform-based quantization…

Machine Learning · Computer Science 2026-04-06 Yasushi Nishida

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits…

Machine Learning · Computer Science 2026-05-14 Hoang-Quan Nguyen , Sankalp Pandey , Khoa Luu

Sequence models based on linear state spaces (SSMs) have recently emerged as a promising choice of architecture for modeling long range dependencies across various modalities. However, they invariably rely on discretization of a continuous…

Machine Learning · Computer Science 2023-11-15 Ankit Gupta , Harsh Mehta , Jonathan Berant